151 citations · 542 across the 33 of their papers we have counts for
5 papers · 1 filter
Accelerating Nonconvex Learning via Replica Exchange Langevin Diffusion
Yi Chen, Jinglin Chen, Jing Dong +2
Langevin diffusion is a powerful method for nonconvex optimization, which enables the escape from local minima by injecting noise into the gradient. In particular, the temperature…
Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatch
Michael Wan, Tanmay Gangwani, Jian Peng
Deep reinforcement learning (RL) algorithms have achieved great success on a wide variety of sequential decision-making tasks. However, many of these algorithms suffer from high sa…
Policy Optimization by Genetic Distillation
Tanmay Gangwani, Jian Peng
Genetic algorithms have been widely used in many practical optimization problems. Inspired by natural selection, operators, including mutation, crossover and selection, provide eff…
Efficient Localized Inference for Large Graphical Models
Jinglin Chen, Jian Peng, Qiang Liu
We propose a new localized inference algorithm for answering marginalization queries in large graphical models with the correlation decay property. Given a query variable and a lar…
Action-depedent Control Variates for Policy Optimization via Stein's Identity
Hao Liu, Yihao Feng, Yi Mao +3
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from the large variance issue on…